Update README.md

README.md

@@ -17,21 +17,20 @@ tags:
 - llama
 - llm
 - text-generation
-- arabic
+- neuralnode
 - multilingual
 - causal-lm
 - horus
 - tokenai
+- tts
+- voice
 datasets:
 - tokenaii/horus-training-data
 metrics: []
 widget:
-  - text: "### User:\nWhat is the capital of Egypt?\n\n### Assistant:"
-    output:
-      text: "The capital of Egypt is Cairo."
-  - text: "### User:\nمن هو أول رئيس لمصر؟\n\n### Assistant:"
-    output:
-      text: "أول رئيس لمصر بعد ثورة 1952 هو محمد نجيب."
+  - text: "### User:\nWhat is the capital of Egypt?\n\n### Assistant:\nThe capital of Egypt is Cairo."
+  - text: "### User:\nمن هو أول رئيس لمصر؟\n\n### Assistant:\nأول رئيس لمصر بعد ثورة 1952 هو محمد نجيب."
+  - text: "### User:\nHello Horus!\n\n### Assistant:\nHello! I'm Horus, an AI assistant developed by TokenAI. How can I help you today?"
 inference: true
 ---
 
@@ -123,26 +122,37 @@ GGUF versions available at: [tokenaii/Hours-1.0-4B-GGUF](https://huggingface.co/
 
 ## Quick Start
 
-### Using Transformers
+### Using NeuralNode (Recommended)
+
+The easiest way to use Horus models is with the NeuralNode framework:
 
 ```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-model = AutoModelForCausalLM.from_pretrained(
-    "tokenaii/horus",
-    subfolder="Horus-1.0-4B",
-    torch_dtype=torch.float16,
-    device_map="auto"
-)
-tokenizer = AutoTokenizer.from_pretrained("tokenaii/horus", subfolder="Horus-1.0-4B")
-
-prompt = "### User:\nHello\n\n### Assistant:"
-inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-outputs = model.generate(**inputs, max_new_tokens=100)
-response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-print(response)
+import neuralnode as nn
+
+MODEL_ID = "tokenaii/Hours-1.0-4B-GGUF/Horus-1.0-4B-Q6_K.gguf"
+DEVICE = "cpu"  # Change to "cuda" for GPU acceleration
+
+# Download and load
+model = nn.HorusModel(MODEL_ID, device=DEVICE).load()
+
+# Use immediately
+response = model.chat([{"role": "user", "content": "hi horus im emy"}])
+
+print(response.content)
 ```
 
+### Select Quantized Version
+
+Choose the best version for your hardware:
+
+| Version | Size | Quality | Code |
+|---------|------|---------|------|
+| F16 | 9.03 GB | Maximum | `Horus-1.0-4B-F16.gguf` |
+| Q8_0 | 4.0 GB | Near lossless | `Horus-1.0-4B-Q8_0.gguf` |
+| Q6_K | 3.71 GB | Excellent | `Horus-1.0-4B-Q6_K.gguf` |
+| Q5_K_M | 3.23 GB | Very Good | `Horus-1.0-4B-Q5_K_M.gguf` |
+| Q4_K_M | 2.78 GB | Good | `Horus-1.0-4B-Q4_K_M.gguf` |
+
 ### Using GGUF with llama.cpp
 
 ```bash